Eventos Anais de eventos
COBEM 2017
24th ABCM International Congress of Mechanical Engineering
Meta-heuristics applied to system identification
Submission Author:
Fábio Meneghetti Ugulino de Araújo , RN
Co-Authors:
Alcemy Gabriel Vitor Severino, Fábio Meneghetti Ugulino de Araújo
Presenter: Mário Sérgio Freitas Ferreira Cavalcante
doi://10.26678/ABCM.COBEM2017.COB17-0542
Abstract
There are different techniques for the problem of identifying systems, many are based on the least squares method and error reduction rate. In this paper meta-heuristics based system identification method are studied to automatically construct NARX models of nonlinear systems of unknown structure from observations of inputs and outputs. The meta-heuristics investigated to system identification are: Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Bat Algorithm (BA). A case study is identified to demonstrate the effectiveness of the meta-heuristics to compare it with traditional identification techniques.
Keywords
meta-heuristic algorithms, nonlinear system identification, Selection of structures, NARX
